Transcribe local audio files using a CPU-based Whisper backend.
npx skills add https://github.com/istota-project/istota --skill whisper-istota-project
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/istota-project/istota/tree/main/src/istota/skills/whisper Command: npx skills add https://github.com/istota-project/istota --skill whisper-istota-project
Local audio transcription on-device, preserving privacy by avoiding cloud processing, and enabling offline workflows with faster-whisper.
Transcribe a local audio file by running istota-skill whisper transcribe /path/to/audio.wav.
High-intent search queries and answers about installing and using this skill.
Local audio transcription with a CPU-based Whisper backend processes files entirely offline, avoiding cloud processing. It validates inputs and handles missing dependencies gracefully to ensure secure, on-device workflows.
Audio transcriptions support multiple output formats including JSON, SRT, VTT, and plain text. You can generate any of these formats across various languages directly from your local audio files.
Automatic model selection evaluates available system RAM to choose the optimal Whisper model for CPU-based transcription. This balances processing speed and accuracy according to your workstation's specific hardware capabilities.
No, a GPU is not required. The transcription process utilizes a CPU-based Whisper backend, automatically selecting the appropriate model based on available RAM to run efficiently on a local, offline workstation.
If dependencies are missing, the transcription process handles the situation gracefully rather than failing abruptly. It validates inputs and returns structured, machine-readable results to help identify and resolve environment issues.
okbest2024Transcribe audio locally using the Whisper CLI without external APIs.
geekatronParse VTT, SRT, and plain text transcripts into structured Markdown packets with action items, decisions, and mindmaps.
aresbitTranscribe audio locally using the Whisper CLI with configurable models and output formats.
martinholovskyTranscribe audio files locally with Faster Whisper speech-to-text.
